24 results about "Discrete optimization" patented technology

The invention belongs to the technical field of additive manufacturing, and particularly relates to a multi-scale parallel optimization method for a lightweight structure based on lattice discrete optimization. According to the method, through multi-scale parallel optimization design, a macro structure and a micro lattice structure are described through geometric parameters of a movable deformation rod piece, an improved two-value coding parameterization method, called a BCP method for short, is adopted to solve discrete optimization of the micro lattice structure, and geometric parameters of an optimization result are easy to extract.

The invention provides a plane layout optimization method and device based on CAD drawing automatic identification, relates to the field of plane layout optimization, and solves the technical problems that only non-overlapping constraints among equipment are considered, actual space obstacles cannot be automatically avoided, and a generated layout scheme cannot be implemented. The method comprises the following steps: extracting barrier data in a layer; and through a parameter configuration mechanism, generating an equipment parameter information structural body containing the mapping relationship between the equipment and the process. And establishing a continuous optimization model containing an IPOPT solver, and obtaining an initial layout solution containing the relative orientation of each device. And based on the relative orientation of each device in the initial layout solution, introducing an obstacle rejection constraint and a device non-overlapping constraint to construct a discrete optimization model, obtaining the center position coordinates of each device through a Gurobi solver, and integrating a dynamic adjustment mechanism and an interlayer relationship optimization mechanism. And generating a new layout map for visual output. The method and the device are used in a plane layout optimization process.

The present application belongs to the technical field of additive manufacturing, and particularly relates to a lightweight structure multi-scale parallel optimization method based on lattice discrete optimization. The present application uses the geometric parameters of movable and deformable rods to describe macroscopic structures and microscopic lattice structures through multi-scale parallel optimization design, and uses an improved double-value coding parameterization method, referred to as BCP method, to solve the discrete optimization of the microscopic lattice structure and easily extract the geometric parameters of the optimization results.

This invention provides a multi-objective relay selection method for energy harvesting cognitive relay networks. In the context of energy harvesting cognitive relay networks, a new multi-objective function is constructed to solve discrete optimization problems by comprehensively considering network energy efficiency and signal-to-noise ratio. The multi-objective relay selection method is then rapidly obtained through a multi-objective quantum monarch butterfly optimization mechanism. This method maximizes network energy efficiency while ensuring the signal-to-noise ratio, providing a new idea and method for solving relay selection schemes in energy harvesting cognitive relay networks.

This invention relates to the field of valve detection technology, and more particularly to a method for detecting internal leakage in valves based on acoustic emission signals. The method includes: acquiring the topology and geometric parameters of the pipeline network to determine the pipeline location characteristics of each valve; based on these characteristics, analyzing the propagation characteristics of acoustic emission signals in the pipe segment where the valve is located for at least two preset frequency bands, and defining the effective monitoring arc segment for each valve in different frequency bands; establishing a dual-modal coverage matrix between the valve and candidate sensor locations, combined with the background noise level; constructing a discrete optimization function based on this matrix to obtain the sensor installation location combination; deploying sensors to collect signals, extracting multi-frequency band time-frequency domain features, and constructing a dual-modal feature vector; combining the feature vector and the coverage matrix to calculate the probability that each valve is a leakage source, and identifying the valve with internal leakage. This invention achieves accurate detection and location of internal leakage in valves by optimizing sensor layout using a dual-modal coverage matrix and fusing multi-frequency band features.

The invention discloses a discrete combination optimization control method of a switchable series-parallel current limiting circuit based on an IGBT and a contactor, and relates to the technical field of power electronic control and electrical testing, the control method comprises the following steps: S1, a real-time sensing step: collecting a target current limiting value and a bus voltage of a system, and real-time state data of each reconfigurable power module, wherein the real-time state data at least comprises a current value, a voltage value and a device temperature. According to the discrete combination optimization control method of the switchable series-parallel current limiting circuit based on the IGBT and the contactor, by dynamically sensing a real-time working condition and constructing a discrete optimization model containing multiple targets, a scheme meeting static and dynamic performance requirements can be automatically and accurately screened out from massive possible topologies; the problems that a traditional fixed topology circuit is limited in adjusting range and insufficient in precision are solved, and the response reliability and the control accuracy of the system under the wide-range working condition are ensured.

The invention belongs to the technical field of data processing, and provides a power market price prediction method and system based on two-stage optimization, and the method comprises the steps: determining an initial generating capacity node value and an initial unit price node value of each generator set, and carrying out the interpolation refining operation of the initial generating capacity node value and the initial unit price node value, obtaining a refined generating capacity node value and a refined unit price node value; establishing an output interval prediction 0-1 planning model of the generator set; performing discrete optimization solution on the output interval prediction 0-1 planning model to obtain a predicted generating capacity interval of each generator set; according to the predicted generating capacity interval, the refined generating capacity node value and the refined unit price node value, establishing an average electricity price prediction quadratic programming model; and performing continuous optimization solution on the average electricity price prediction quadratic programming model to obtain an average electricity price prediction value. The scheme can adapt to market dynamic changes, and prediction precision, flexibility and reliability are effectively improved.

Techniques are described for processing measurement information to select a respective label for multiple voxels or pixels of a medical image dataset. Reference information is described comprising a respective reference dataset for each one of the possible labels, and each label is associated with a material parameter. A respective label for the respective voxel or pixel is selected by using a discrete optimization algorithm to optimize a cost function comprising a first partial cost function and a second partial cost function, and the incorporation of the second partial cost function into the cost function introduces a coupling between the labels at different voxels or pixels.

Techniques for configuring an entity are disclosed. The techniques include generating, based on multiple sets of features inputted into a machine learning model, predictions of multiple sets of performance metrics for multiple configurations of the entity. The techniques also include calculating a change in efficiency between each configuration in the multiple configurations and the base configuration based on a first set of performance metrics for the base configuration and a second set of performance metrics generated by the machine learning model for the configuration. The techniques further include determining, based on values of the change in efficiency calculated for the multiple configurations, a second set of configuration values with a highest increase in efficiency over the base configuration. The techniques additionally include causing the second set of configuration values to be outputted in association with the entity.

The invention discloses a fine-grained visual classification method and system based on adaptive attention quantization Transform. The system comprises an adaptive quantization selection module, a background elimination module and a dynamic hybrid optimization module. The self-adaptive quantization selection module dynamically selects attention scores of a plurality of attention heads by introducing a global and learnable threshold value and adopting a binary quantization mode, selects the most distinguishing feature, and effectively reduces the dilution of attention of the attention head focused on a non-distinguishing mark on a distinguishing area. And meanwhile, discrete optimization is carried out by adopting a straight-through estimator, so that gradient back propagation is realized. And the background elimination module removes features containing background information, so that interference of background noise is eliminated. And the dynamic hybrid optimization module dynamically optimizes and integrates selection and elimination branches so as to realize an optimal classification effect. Experiments prove that the method achieves the current advanced performance on the fine-grained visual classification task.

The invention discloses a traffic signal control optimization method, system, equipment and medium, and relates to the technical field of traffic management, and the method comprises the steps: obtaining vehicle trajectory data, and carrying out the flow reduction processing of the trajectory data, and obtaining the traffic flow; on the basis of traffic flow, signal timing and vehicle speed parameters are introduced, and delay of signals at different intersections is generated in combination with a support vector regression algorithm; the total delay time is minimized by adjusting the phase difference of signals at different intersections, the particle swarm optimization algorithm is improved by introducing dynamic target weight adjustment, the weight ratio between delay and traffic efficiency is adjusted according to the evolutionary process of particles and the current search condition, and the optimal traffic signal control scheme is obtained. According to the algorithm, through a dynamic weight adjustment mechanism and a particle forgetting mechanism, the convergence speed and the global search capability of a phase difference optimization process can be improved, and the defects of a traditional PSO algorithm in a discrete optimization problem are overcome.

The application relates to a causal DAG discovery method for an online service system based on fusion of soft priori. The method comprises the following steps: obtaining observation data and text meta-knowledge of the service system, preprocessing to form a standardized sample set, identifying variable types and semantics and outputting; generating a natural language description according to the variable semantics, querying a large language model for an ordered variable pair, analyzing to obtain three types of causal probability vectors, and calibrating to obtain an edge-level priori probability. An appropriate conditional independence test method is selected, high-confidence independent / dependent sentences are divided, and weights are assigned. A candidate directed acyclic graph is selected as an initial structure, parameters are estimated by linear regression, and data fitting scores are calculated, language priori scores, conditional independence penalty terms and counterfactual self-consistency penalty terms are calculated. Fusion is carried out into a hybrid score function, discrete optimization is carried out under the constraint of a directed acyclic graph, and a causal graph structure with the optimal score is output. The method can improve the efficiency and accuracy of a smart operation and maintenance system.

There is provided a non-transitory computer-readable medium storing a calculation program for causing a computer to execute a process. The process includes, an embedding vector generation process for generating an embedding vector that represents each similarity of each problem for multiple problems, in optimization using a continuous relaxation simulated annealing method, which searches for a solution by incorporating continuous relaxation to discrete optimization problems, and a search process for introducing a loss term based on the embedding vector into a loss function in which each element of a matrix obtained by relaxing discrete variables to be optimized into a continuous matrix becomes a discrete optimization problem, and searching for solutions of the multiple problems in parallel.

The present application relates to the technical field of unmanned cluster cooperative task allocation, and particularly relates to an unmanned cluster task allocation method based on an improved swarm intelligence algorithm, comprising the following steps: S1, modeling the unmanned cluster cooperative task allocation as a multi-objective discrete optimization, and constructing a corresponding multi-objective optimization model; S2, using an improved multi-objective pelican optimization algorithm to solve the multi-objective optimization model, and the improvement of the multi-objective pelican optimization algorithm comprises: introducing an external archive strategy, a fast non-dominated sorting mechanism and a crowdedness comparison operator; the unmanned cluster task allocation method based on the improved swarm intelligence algorithm, by using the improved multi-objective pelican optimization algorithm as a solver and introducing the external archive strategy, the fast non-dominated sorting mechanism and the crowdedness comparison operator, the present application effectively solves the defects of slow convergence speed, easy to fall into a local optimal solution, insufficient diversity of solutions and weak adaptability of traditional swarm intelligence algorithms when solving multi-objective discrete problems.

There is provided a non-transitory computer-readable medium storing a calculation program for causing a computer to execute a process. The process includes, in a cost function in a search process that performs a search by incorporating continuous relaxation into a discrete optimization problem, in which each element of a matrix obtained by relaxing discrete variables to be optimized into a continuous matrix is a solution of a plurality of discrete optimization problems, outputting a solution of a discrete optimization problem using solutions of the plurality of discrete optimization problems obtained by training a machine learning model by applying a perturbation to the plurality of discrete optimization problems.

This application relates to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for optimizing parameters of a hydrogen fuel nozzle. The method includes: acquiring a set of structural parameters; classifying each parameter combination using a first classification model and various second classification models, determining the first discrete index classification result and the second discrete index classification result corresponding to each parameter combination; determining the parameter analysis result for each parameter combination using a preset parameter analysis algorithm and the first and second discrete index classification results; determining the target parameter and its corresponding target parameter range among various types of structural parameters based on a preset discrete optimization objective and the contribution degree and direction in the parameter analysis results; and optimizing the target parameter combination based on the target parameter range and a preset continuous evaluation index to obtain the optimized target parameter value. This method can improve the accuracy of parameter optimization.

The invention discloses a region coverage discrete optimization and attitude maneuver planning method for a satellite with a rotary table, and belongs to the technical field of satellite application and observation planning. According to the method, through regional grid division and candidate strip set generation in any direction, an optimized strip capable of achieving the maximum regional coverage rate with the minimum number is obtained through integer programming modeling solution. According to the method, a two-dimensional turntable rotation angle sequence meeting pointing constraint and speed parallel constraint is planned, and a body attitude quaternion trajectory of satellite execution stripe push-broom imaging is obtained through derivation based on minimum Euler rotation. And for attitude pointing switching between strips, quaternion spherical linear interpolation is carried out on an initial quaternion and a target quaternion by designing an Euler rotation angular velocity trajectory, and a continuous rapid attitude maneuver trajectory is obtained. According to the region coverage discrete optimization and attitude maneuver planning method, generation of optimization coverage strips in any direction is allowed, region coverage attitude maneuver gaps are reduced, and observation task execution efficiency is improved.

This invention discloses a transient coordinated control method for solid waste thermal storage and power grid frequency regulation commands. This method, for the first time, proposes a transient coupling model of heat flux density field-phase change excitation, overcoming the constraint of thermal inertia. Through cross-domain integration of discrete optimization algorithms, field strength allocation technology, and holographic simulation technology, it solves the time-domain mismatch problem and achieves transient coordinated control of solid waste thermal storage and power grid frequency regulation commands. The proposed transient coordinated control method for solid waste thermal storage and power grid frequency regulation commands aims to establish a transient coupling model between power grid commands, heat flux density field, and phase change excitation. Through micro-domain phase change excitation and virtual pre-simulation compensation mechanisms, it reduces the thermal response delay from the 300-second level to the sub-second level, improves temperature control accuracy by 50 times, breaks through the theoretical limit of 95% energy conversion efficiency, and achieves a power grid frequency regulation command matching degree of 99.3%. This effectively solves the problems of slow thermal response speed, low energy conversion efficiency, and poor matching degree with power grid commands in existing technologies.

The invention discloses an electric quantity transaction monitoring method and system based on multi-source data, and the method comprises the steps: calculating a historical load fluctuation coefficient, and carrying out the first-level division, and obtaining a user terminal set; acquiring a real-time load data sequence and extracting real-time load characteristics; performing second-level division on the user terminal set in combination with the static attribute data and the real-time load characteristics to obtain user terminal subsets; selecting a target user terminal in the subset based on the historical load fluctuation coefficient interval, and performing electric quantity transaction detection to obtain a transaction degree set; calculating dispersion and optimizing the transaction degree set by adopting a screening strategy to obtain a target transaction degree set; and determining the electric quantity transaction degree of each user terminal in the subset according to the target transaction degree. According to the invention, through a collaborative mechanism of double-layer classification, representative selection, dynamic detection, discrete optimization and result inference, the accuracy and high efficiency of electric quantity transaction monitoring are realized.

The application relates to a radar waveform design method and device, computer equipment and a storage medium. The method comprises the following steps: determining a target echo signal according to a radar receiver; constructing a radar echo optimization model by taking the waveform energy and the waveform equivalent bandwidth of the target echo signal as design variables and maximizing the echo signal-to-noise ratio as an optimization target; discretely decomposing the radar echo optimization model to obtain a discrete optimization model; approximating the discrete optimization model by using the Dirac-Bach rule to obtain a second-order cone programming model; iteratively solving the second-order cone programming model by using a second-order cone programming algorithm to obtain a transmission waveform power spectrum of the radar echo optimization model; and synthesizing the transmission waveform power spectrum by using a phase recovery algorithm to obtain a radar optimization time-domain waveform. The method can overcome the problem of performance loss of a heuristic signal-to-noise ratio and guarantee the high-precision requirements of target tracking and measurement.

According to the sewage treatment process water quantity aeration element scheduling method based on double-layer particle swarm optimization, water quantity aeration double-layer scheduling optimization operation in the sewage treatment process is achieved, the effluent quality is guaranteed, and the treatment energy consumption is reduced. In a sewage treatment process, a plurality of mutually coupled and nested treatment processes exist, and a water quantity process and an aeration process have crucial influences on sewage treatment indexes. However, compared with the mutual nesting influence of two processes, the conventional optimization method can cause the waste of a large amount of computing resources and is difficult to efficiently obtain a scheduling decision scheme. Therefore, a sewage treatment double-layer water volume aeration scheduling model is established, and a double-layer particle swarm optimization method is designed. According to the method, a discrete optimization space is efficiently searched through a distributed particle swarm representation method, and a high-quality lower-layer task is selected for solving by using a density-based clustering method, so that operation resources are greatly saved, and efficient decision-making of the water aeration optimization scheduling problem in the sewage treatment process is realized.

The invention belongs to the technical field of motor driving control, particularly relates to a dual-three-phase motor current harmonic suppression method based on a discrete optimization repetitive expansion state observer, and aims to realize consideration of overall disturbance suppression of a system and precise suppression of specific-order harmonics. And the harmonic suppression problem of disturbance response performance of other frequency bands cannot be lost. The method comprises the following steps: acquiring a torque subspace and harmonic subspace mathematical model of the dual three-phase motor under a synchronous rotating coordinate system; discretizing the harmonic subspace mathematical model; constructing an expansion state space expression containing total disturbance; constructing a second-order discrete expansion state observer on the basis; and constructing a discrete optimization repetitive controller, and embedding the discrete optimization repetitive controller into a disturbance estimation channel of the second-order discrete expansion state observer to obtain the discrete optimization repetitive expansion state observer. According to the harmonic suppression method provided by the invention, the harmonic at the target frequency can be accurately suppressed, and the disturbance suppression performance of other frequency bands cannot be lost.

The application provides a resource allocation method for an ultra-dense low-orbit satellite network, comprising the following steps: constructing a joint optimization model with the target of minimizing the total weighted energy consumption of the system, the joint optimization model being limited by co-channel interference and time delay constraints; generating an initial feasible solution of the joint optimization model under the condition of meeting the constraints; under the premise of fixing the continuous resource variables, updating the calculation offloading decision variables of the joint optimization model by iteratively optimizing the matching relationship between the tasks and the satellite-channel units; under the premise of fixing the calculation offloading decision variables, jointly optimizing the user terminal transmission power and the satellite calculation resource allocation amount; alternately performing a discrete optimization stage and a continuous optimization stage until a preset convergence condition is met, and obtaining an optimal offloading decision and a resource allocation scheme; and controlling the user terminal and the satellite to perform task offloading and resource allocation according to the optimal offloading decision and the resource allocation scheme.